{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T04:02:40Z","timestamp":1750737760657,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819665785","type":"print"},{"value":"9789819665792","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-6579-2_13","type":"book-chapter","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T12:06:45Z","timestamp":1750680405000},"page":"182-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RBHAR: Role-Based Heterogeneous Action Representation in\u00a0Multi-agent Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2881-5795","authenticated-orcid":false,"given":"Jiaosai","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1610-2338","authenticated-orcid":false,"given":"Zhen","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8520-7539","authenticated-orcid":false,"given":"Zhenfeng","family":"Su","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8074-637X","authenticated-orcid":false,"given":"Zhiming","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"issue":"1","key":"13_CR1","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1109\/TII.2012.2219061","volume":"9","author":"Y Cao","year":"2012","unstructured":"Cao, Y., Yu, W., Ren, W., Chen, G.: An overview of recent progress in the study of distributed multi-agent coordination. IEEE Trans. Industr. Inf. 9(1), 427\u2013438 (2012)","journal-title":"IEEE Trans. Industr. Inf."},{"key":"13_CR2","unstructured":"Chen, Y., et al.: PTDE: Personalized training with distillated execution for multi-agent reinforcement learning. arXiv preprint arXiv:2210.08872 (2022)"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Ma4div: Multi-agent reinforcement learning for search result diversification. arXiv preprint arXiv:2403.17421 (2024)","DOI":"10.1145\/3696410.3714862"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Yang, W., Zhang, T., Wu, S., Chang, H.: Commander-soldiers reinforcement learning for cooperative multi-agent systems. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20137. IEEE (2022)","DOI":"10.1109\/IJCNN55064.2022.9892794"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Du, W., Ding, S., Zhang, C., Shi, Z.: Multiagent reinforcement learning with heterogeneous graph attention network. IEEE Transactions on Neural Networks and Learning Systems (2022)","DOI":"10.1109\/TNNLS.2022.3215774"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"issue":"2","key":"13_CR7","doi-asserted-by":"publisher","first-page":"3033","DOI":"10.1016\/j.ifacol.2023.10.1431","volume":"56","author":"Q Fu","year":"2023","unstructured":"Fu, Q., Ai, X., Yi, J., Qiu, T., Yuan, W., Pu, Z.: Learning heterogeneous agent cooperation via multiagent league training. IFAC-PapersOnLine 56(2), 3033\u20133040 (2023)","journal-title":"IFAC-PapersOnLine"},{"key":"13_CR8","unstructured":"Iqbal, S., De\u00a0Witt, C.A.S., Peng, B., B\u00f6hmer, W., Whiteson, S., Sha, F.: Randomized entity-wise factorization for multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4596\u20134606. PMLR (2021)"},{"key":"13_CR9","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.neucom.2016.01.031","volume":"190","author":"L Kraemer","year":"2016","unstructured":"Kraemer, L., Banerjee, B.: Multi-agent reinforcement learning as a rehearsal for decentralized planning. Neurocomputing 190, 82\u201394 (2016)","journal-title":"Neurocomputing"},{"key":"13_CR10","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter\u00a0Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"issue":"10","key":"13_CR11","doi-asserted-by":"publisher","first-page":"2239","DOI":"10.1109\/JSAC.2019.2933973","volume":"37","author":"YS Nasir","year":"2019","unstructured":"Nasir, Y.S., Guo, D.: Multi-agent deep reinforcement learning for dynamic power allocation in wireless networks. IEEE J. Sel. Areas Commun. 37(10), 2239\u20132250 (2019)","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Oliehoek, F.A., Amato, C., et\u00a0al.: A concise introduction to decentralized POMDPs, vol.\u00a01. Springer (2016)","DOI":"10.1007\/978-3-319-28929-8_1"},{"key":"13_CR13","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1613\/jair.2447","volume":"32","author":"FA Oliehoek","year":"2008","unstructured":"Oliehoek, F.A., Spaan, M.T., Vlassis, N.: Optimal and approximate q-value functions for decentralized pomdps. J. Artif. Intell. Res. 32, 289\u2013353 (2008)","journal-title":"J. Artif. Intell. Res."},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Pav\u00f3n, J., G\u00f3mez-Sanz, J.: Agent oriented software engineering with ingenias. In: International Central and Eastern European Conference on Multi-Agent Systems, pp. 394\u2013403. Springer (2003)","DOI":"10.1007\/3-540-45023-8_38"},{"key":"13_CR15","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., Farquhar, G., Foerster, J., Whiteson, S.: Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4295\u20134304. PMLR (2018)"},{"key":"13_CR16","unstructured":"Samvelyan, M., et al.: The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043 (2019)"},{"key":"13_CR17","unstructured":"Son, K., Kim, D., Kang, W.J., Hostallero, D.E., Yi, Y.: QTRAN: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 5887\u20135896. PMLR (2019)"},{"key":"13_CR18","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/978-3-642-22636-6_7","volume-title":"Agent-Oriented Software Engineering XI","author":"N Spanoudakis","year":"2011","unstructured":"Spanoudakis, N., Moraitis, P.: Using ASEME methodology for model-driven agent systems development. In: Weyns, D., Gleizes, M.-P. (eds.) Agent-Oriented Software Engineering XI, pp. 106\u2013127. Springer Berlin Heidelberg, Berlin, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-22636-6_7"},{"key":"13_CR19","unstructured":"Sunehag, P., et\u00a0al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"issue":"4","key":"13_CR20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395","volume":"12","author":"A Tampuu","year":"2017","unstructured":"Tampuu, A., et al.: Multiagent cooperation and competition with deep reinforcement learning. PLoS ONE 12(4), e0172395 (2017)","journal-title":"PLoS ONE"},{"issue":"7782","key":"13_CR21","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"},{"key":"13_CR22","unstructured":"Wang, J., Ren, Z., Liu, T., Yu, Y., Zhang, C.: Qplex: duplex dueling multi-agent q-learning. In: International Conference on Learning Representations (2020)"},{"key":"13_CR23","unstructured":"Wang, T., Dong, H., Lesser, V., Zhang, C.: Roma: multi-agent reinforcement learning with emergent roles. In: International Conference on Machine Learning, pp. 9876\u20139886. PMLR (2020)"},{"key":"13_CR24","unstructured":"Wang, T., Gupta, T., Mahajan, A., Peng, B., Whiteson, S., Zhang, C.: Rode: learning roles to decompose multi-agent tasks. In: International Conference on Learning Representations (2020)"},{"key":"13_CR25","unstructured":"Wang, W., et al.: Action semantics network: considering the effects of actions in multiagent systems. In: International Conference on Learning Representations (2019)"},{"key":"13_CR26","first-page":"1698","volume":"35","author":"M Yang","year":"2022","unstructured":"Yang, M., Zhao, J., Hu, X., Zhou, W., Zhu, J., Li, H.: LDSA: learning dynamic subtask assignment in cooperative multi-agent reinforcement learning. Adv. Neural. Inf. Process. Syst. 35, 1698\u20131710 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR27","unstructured":"Yang, Y., et al.: Qatten: A general framework for cooperative multiagent reinforcement learning. arXiv preprint arXiv:2002.03939 (2020)"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Zhu, H., Zhou, M.: Role-based multi-agent systems. In: Personalized Information Retrieval and Access: Concepts, Methods and Practices, pp. 254\u2013285. IGI Global (2008)","DOI":"10.4018\/978-1-59904-510-8.ch012"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6579-2_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T12:06:53Z","timestamp":1750680413000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6579-2_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819665785","9789819665792"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6579-2_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}